Update app.py

app.py

@@ -27,41 +27,42 @@ Helpful answer:
 
 prompt = PromptTemplate(template=template, input_variables=["context", "question"])
 
-
-# Load and process the PDF
-loader = PyPDFLoader(pdf_file.name)
-pdf_data = loader.load()
-
-# Split the text into chunks
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-docs = text_splitter.split_documents(pdf_data)
-
-# Create a Chroma vector store
-embeddings = HuggingFaceEmbeddings(model_name="embaas/sentence-transformers-multilingual-e5-base")
-db = Chroma.from_documents(docs, embeddings)
-
-# Initialize message history for conversation
-message_history = ChatMessageHistory()
-
-# Memory for conversational context
-memory = ConversationBufferMemory(
-       memory_key="chat_history",
-       output_key="answer",
-       chat_memory=message_history,
-       return_messages=True,
-   )
-
-# Create a chain that uses the Chroma vector store
-chain = ConversationalRetrievalChain.from_llm(
-        llm=llm,
-        chain_type="stuff",
-        retriever=db.as_retriever(),
-        memory=memory,
-        return_source_documents=False,
-        combine_docs_chain_kwargs={'prompt': prompt}
-    )
-
-# Process the question
-res = chain({"question": question})
-answer = res["answer"]
+def process_pdf_and_ask_question(pdf_file,question):
+    # Load and process the PDF
+    loader = PyPDFLoader(pdf_file.name)
+    pdf_data = loader.load()
+    
+    # Split the text into chunks
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    docs = text_splitter.split_documents(pdf_data)
+    
+    # Create a Chroma vector store
+    embeddings = HuggingFaceEmbeddings(model_name="embaas/sentence-transformers-multilingual-e5-base")
+    db = Chroma.from_documents(docs, embeddings)
+    
+    # Initialize message history for conversation
+    message_history = ChatMessageHistory()
+    
+    # Memory for conversational context
+    memory = ConversationBufferMemory(
+           memory_key="chat_history",
+           output_key="answer",
+           chat_memory=message_history,
+           return_messages=True,
+       )
+    
+    # Create a chain that uses the Chroma vector store
+    chain = ConversationalRetrievalChain.from_llm(
+            llm=llm,
+            chain_type="stuff",
+            retriever=db.as_retriever(),
+            memory=memory,
+            return_source_documents=False,
+            combine_docs_chain_kwargs={'prompt': prompt}
+        )
+    
+    # Process the question
+    res = chain({"question": question})
+    return res["answer"]
+